head	1.1;
branch	1.1.1;
access;
symbols
	netbsd-11-0-RC5:1.1.1.2
	netbsd-11-0-RC4:1.1.1.2
	netbsd-11-0-RC3:1.1.1.2
	netbsd-11-0-RC2:1.1.1.2
	netbsd-11-0-RC1:1.1.1.2
	perseant-exfatfs-base-20250801:1.1.1.2
	netbsd-11:1.1.1.2.0.18
	netbsd-11-base:1.1.1.2
	netbsd-10-1-RELEASE:1.1.1.2
	perseant-exfatfs-base-20240630:1.1.1.2
	perseant-exfatfs:1.1.1.2.0.16
	perseant-exfatfs-base:1.1.1.2
	netbsd-8-3-RELEASE:1.1.1.1
	netbsd-9-4-RELEASE:1.1.1.2
	netbsd-10-0-RELEASE:1.1.1.2
	netbsd-10-0-RC6:1.1.1.2
	netbsd-10-0-RC5:1.1.1.2
	netbsd-10-0-RC4:1.1.1.2
	netbsd-10-0-RC3:1.1.1.2
	netbsd-10-0-RC2:1.1.1.2
	netbsd-10-0-RC1:1.1.1.2
	netbsd-10:1.1.1.2.0.14
	netbsd-10-base:1.1.1.2
	netbsd-9-3-RELEASE:1.1.1.2
	gmp-6-2-1:1.1.1.2
	cjep_sun2x-base1:1.1.1.2
	cjep_sun2x:1.1.1.2.0.12
	cjep_sun2x-base:1.1.1.2
	cjep_staticlib_x-base1:1.1.1.2
	netbsd-9-2-RELEASE:1.1.1.2
	cjep_staticlib_x:1.1.1.2.0.10
	cjep_staticlib_x-base:1.1.1.2
	netbsd-9-1-RELEASE:1.1.1.2
	gmp-6-2-0:1.1.1.2
	phil-wifi-20200421:1.1.1.2
	phil-wifi-20200411:1.1.1.2
	is-mlppp:1.1.1.2.0.8
	is-mlppp-base:1.1.1.2
	phil-wifi-20200406:1.1.1.2
	netbsd-8-2-RELEASE:1.1.1.1
	netbsd-9-0-RELEASE:1.1.1.2
	netbsd-9-0-RC2:1.1.1.2
	netbsd-9-0-RC1:1.1.1.2
	phil-wifi-20191119:1.1.1.2
	netbsd-9:1.1.1.2.0.6
	netbsd-9-base:1.1.1.2
	phil-wifi-20190609:1.1.1.2
	netbsd-8-1-RELEASE:1.1.1.1
	netbsd-8-1-RC1:1.1.1.1
	pgoyette-compat-merge-20190127:1.1.1.2
	pgoyette-compat-20190127:1.1.1.2
	pgoyette-compat-20190118:1.1.1.2
	pgoyette-compat-1226:1.1.1.2
	pgoyette-compat-1126:1.1.1.2
	pgoyette-compat-1020:1.1.1.2
	pgoyette-compat-0930:1.1.1.2
	pgoyette-compat-0906:1.1.1.2
	netbsd-7-2-RELEASE:1.1.1.1
	pgoyette-compat-0728:1.1.1.2
	netbsd-8-0-RELEASE:1.1.1.1
	phil-wifi:1.1.1.2.0.4
	phil-wifi-base:1.1.1.2
	pgoyette-compat-0625:1.1.1.2
	netbsd-8-0-RC2:1.1.1.1
	pgoyette-compat-0521:1.1.1.2
	pgoyette-compat-0502:1.1.1.2
	pgoyette-compat-0422:1.1.1.2
	netbsd-8-0-RC1:1.1.1.1
	pgoyette-compat-0415:1.1.1.2
	pgoyette-compat-0407:1.1.1.2
	pgoyette-compat-0330:1.1.1.2
	pgoyette-compat-0322:1.1.1.2
	pgoyette-compat-0315:1.1.1.2
	netbsd-7-1-2-RELEASE:1.1.1.1
	pgoyette-compat:1.1.1.2.0.2
	pgoyette-compat-base:1.1.1.2
	netbsd-7-1-1-RELEASE:1.1.1.1
	matt-nb8-mediatek:1.1.1.1.0.26
	matt-nb8-mediatek-base:1.1.1.1
	gmp-6-1-2:1.1.1.2
	perseant-stdc-iso10646:1.1.1.1.0.24
	perseant-stdc-iso10646-base:1.1.1.1
	netbsd-8:1.1.1.1.0.22
	netbsd-8-base:1.1.1.1
	prg-localcount2-base3:1.1.1.1
	prg-localcount2-base2:1.1.1.1
	prg-localcount2-base1:1.1.1.1
	prg-localcount2:1.1.1.1.0.20
	prg-localcount2-base:1.1.1.1
	pgoyette-localcount-20170426:1.1.1.1
	bouyer-socketcan-base1:1.1.1.1
	pgoyette-localcount-20170320:1.1.1.1
	netbsd-7-1:1.1.1.1.0.18
	netbsd-7-1-RELEASE:1.1.1.1
	netbsd-7-1-RC2:1.1.1.1
	netbsd-7-nhusb-base-20170116:1.1.1.1
	bouyer-socketcan:1.1.1.1.0.16
	bouyer-socketcan-base:1.1.1.1
	pgoyette-localcount-20170107:1.1.1.1
	netbsd-7-1-RC1:1.1.1.1
	pgoyette-localcount-20161104:1.1.1.1
	netbsd-7-0-2-RELEASE:1.1.1.1
	localcount-20160914:1.1.1.1
	netbsd-7-nhusb:1.1.1.1.0.14
	netbsd-7-nhusb-base:1.1.1.1
	pgoyette-localcount-20160806:1.1.1.1
	pgoyette-localcount-20160726:1.1.1.1
	pgoyette-localcount:1.1.1.1.0.12
	pgoyette-localcount-base:1.1.1.1
	netbsd-7-0-1-RELEASE:1.1.1.1
	netbsd-7-0:1.1.1.1.0.10
	netbsd-7-0-RELEASE:1.1.1.1
	netbsd-7-0-RC3:1.1.1.1
	netbsd-7-0-RC2:1.1.1.1
	netbsd-7-0-RC1:1.1.1.1
	tls-maxphys-base:1.1.1.1
	tls-maxphys:1.1.1.1.0.8
	netbsd-7:1.1.1.1.0.6
	netbsd-7-base:1.1.1.1
	yamt-pagecache:1.1.1.1.0.4
	yamt-pagecache-base9:1.1.1.1
	tls-earlyentropy:1.1.1.1.0.2
	tls-earlyentropy-base:1.1.1.1
	riastradh-xf86-video-intel-2-7-1-pre-2-21-15:1.1.1.1
	riastradh-drm2-base3:1.1.1.1
	gmp-5-1-3:1.1.1.1
	gmp:1.1.1;
locks; strict;
comment	@;; @;


1.1
date	2013.11.29.07.49.49;	author mrg;	state Exp;
branches
	1.1.1.1;
next	;
commitid	L2Av4PuGmdoL39fx;

1.1.1.1
date	2013.11.29.07.49.49;	author mrg;	state Exp;
branches
	1.1.1.1.4.1
	1.1.1.1.8.1;
next	1.1.1.2;
commitid	L2Av4PuGmdoL39fx;

1.1.1.2
date	2017.08.22.09.40.49;	author mrg;	state Exp;
branches;
next	;
commitid	W5kmAIk8hwVpSb4A;

1.1.1.1.4.1
date	2013.11.29.07.49.49;	author yamt;	state dead;
branches;
next	1.1.1.1.4.2;
commitid	nx2BSsHy0NPeAxBx;

1.1.1.1.4.2
date	2014.05.22.14.09.05;	author yamt;	state Exp;
branches;
next	;
commitid	nx2BSsHy0NPeAxBx;

1.1.1.1.8.1
date	2013.11.29.07.49.49;	author tls;	state dead;
branches;
next	1.1.1.1.8.2;
commitid	jTnpym9Qu0o4R1Nx;

1.1.1.1.8.2
date	2014.08.19.23.59.54;	author tls;	state Exp;
branches;
next	;
commitid	jTnpym9Qu0o4R1Nx;


desc
@@


1.1
log
@Initial revision
@
text
@dnl  x86 mpn_sqr_basecase -- square an mpn number, optimised for atom.

dnl  Contributed to the GNU project by Torbjorn Granlund and Marco Bodrato.
dnl
dnl  Copyright 2011 Free Software Foundation, Inc.
dnl
dnl  This file is part of the GNU MP Library.
dnl
dnl  The GNU MP Library is free software; you can redistribute it and/or modify
dnl  it under the terms of the GNU Lesser General Public License as published
dnl  by the Free Software Foundation; either version 3 of the License, or (at
dnl  your option) any later version.
dnl
dnl  The GNU MP Library is distributed in the hope that it will be useful, but
dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
dnl  License for more details.
dnl
dnl  You should have received a copy of the GNU Lesser General Public License
dnl  along with the GNU MP Library.  If not, see http://www.gnu.org/licenses/.

include(`../config.m4')

C TODO
C  * Check if 'jmp N(%esp)' is well-predicted enough to allow us to combine the
C    4 large loops into one; we could use it for the outer loop branch.
C  * Optimise code outside of inner loops.
C  * Write combined addmul_1 feed-in a wind-down code, and use when iterating
C    outer each loop.  ("Overlapping software pipelining")
C  * Perhaps use caller-saves regs for inlined mul_1, allowing us to postpone
C    all pushes.
C  * Perhaps write special code for n < M, for some small M.
C  * Replace inlined addmul_1 with smaller code from aorsmul_1.asm, or perhaps
C    with even less pipelined code.
C  * We run the outer loop until we have a 2-limb by 1-limb addmul_1 left.
C    Consider breaking out earlier, saving high the cost of short loops.

C void mpn_sqr_basecase (mp_ptr wp,
C                        mp_srcptr xp, mp_size_t xn);

define(`rp',  `%edi')
define(`up',  `%esi')
define(`n',   `%ecx')

define(`un',  `%ebp')

	TEXT
	ALIGN(16)
PROLOGUE(mpn_sqr_basecase)
	push	%edi
	push	%esi
	mov	12(%esp), rp
	mov	16(%esp), up
	mov	20(%esp), n

	lea	4(rp), rp	C write triangular product starting at rp[1]
	dec	n
	movd	(up), %mm7

	jz	L(one)
	lea	4(up), up
	push	%ebx
	push	%ebp
	mov	n, %eax

	movd	(up), %mm0
	neg	n
	pmuludq	%mm7, %mm0
	pxor	%mm6, %mm6
	mov	n, un

	and	$3, %eax
	jz	L(of0)
	cmp	$2, %eax
	jc	L(of1)
	jz	L(of2)

C ================================================================
	jmp	L(m3)
	ALIGN(16)
L(lm3):	movd	-4(up), %mm0
	pmuludq	%mm7, %mm0
	psrlq	$32, %mm6
	lea	16(rp), rp
	paddq	%mm0, %mm6
	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -4(rp)
	psrlq	$32, %mm6
L(m3):	paddq	%mm0, %mm6
	movd	4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, (rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, 4(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	add	$4, un
	movd	%mm6, 8(rp)
	lea	16(up), up
	js	L(lm3)

	psrlq	$32, %mm6
	movd	%mm6, 12(rp)

	inc	n
C	jz	L(done)
  lea	-12(up), up
  lea	4(rp), rp
	jmp	L(ol2)

C ================================================================
	ALIGN(16)
L(lm0):	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	psrlq	$32, %mm6
	lea	16(rp), rp
L(of0):	paddq	%mm0, %mm6
	movd	4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, (rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, 4(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	12(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, 8(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	add	$4, un
	movd	%mm6, 12(rp)
	lea	16(up), up
	js	L(lm0)

	psrlq	$32, %mm6
	movd	%mm6, 16(rp)

	inc	n
C	jz	L(done)
  lea	-8(up), up
  lea	8(rp), rp
	jmp	L(ol3)

C ================================================================
	ALIGN(16)
L(lm1):	movd	-12(up), %mm0
	pmuludq	%mm7, %mm0
	psrlq	$32, %mm6
	lea	16(rp), rp
	paddq	%mm0, %mm6
	movd	-8(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -12(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	-4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -8(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -4(rp)
	psrlq	$32, %mm6
L(of1):	paddq	%mm0, %mm6
	add	$4, un
	movd	%mm6, (rp)
	lea	16(up), up
	js	L(lm1)

	psrlq	$32, %mm6
	movd	%mm6, 4(rp)

	inc	n
	jz	L(done)		C goes away when we add special n=2 code
  lea	-20(up), up
  lea	-4(rp), rp
	jmp	L(ol0)

C ================================================================
	ALIGN(16)
L(lm2):	movd	-8(up), %mm0
	pmuludq	%mm7, %mm0
	psrlq	$32, %mm6
	lea	16(rp), rp
	paddq	%mm0, %mm6
	movd	-4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -8(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -4(rp)
	psrlq	$32, %mm6
L(of2):	paddq	%mm0, %mm6
	movd	4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, (rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	add	$4, un
	movd	%mm6, 4(rp)
	lea	16(up), up
	js	L(lm2)

	psrlq	$32, %mm6
	movd	%mm6, 8(rp)

	inc	n
C	jz	L(done)
  lea	-16(up), up
C  lea	(rp), rp
C	jmp	L(ol1)

C ================================================================

L(ol1):	lea	4(up,n,4), up
	movd	(up), %mm7	C read next U invariant limb
	lea	8(rp,n,4), rp
	mov	n, un

	movd	4(up), %mm1
	pmuludq	%mm7, %mm1
	sar	$2, un
	movd	%mm1, %ebx
	inc	un
	jz	L(re1)

	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	xor	%edx, %edx	C zero edx and CF
	jmp	L(a1)

L(la1):	adc	$0, %edx
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	adc	$0, %edx
	add	%eax, (rp)
L(a1):	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	movd	%mm0, %eax
	movd	12(up), %mm1
	pmuludq	%mm7, %mm1
	adc	$0, %edx
	add	%ebx, 4(rp)
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	lea	16(up), up
	movd	(up), %mm0
	adc	$0, %edx
	add	%eax, 8(rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	pmuludq	%mm7, %mm0
	inc	un
	movd	4(up), %mm1
	jnz	L(la1)

	adc	un, %edx	C un is zero here
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	adc	un, %eax
	add	%ebx, 4(rp)
	adc	un, %eax
	mov	%eax, 8(rp)

	inc	n

C ================================================================

L(ol0):	lea	(up,n,4), up
	movd	4(up), %mm7	C read next U invariant limb
	lea	4(rp,n,4), rp
	mov	n, un

	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	sar	$2, un
	movd	12(up), %mm1
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	xor	%edx, %edx	C zero edx and CF
	jmp	L(a0)

L(la0):	adc	$0, %edx
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	adc	$0, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	movd	%mm0, %eax
	movd	12(up), %mm1
	pmuludq	%mm7, %mm1
	adc	$0, %edx
	add	%ebx, 4(rp)
L(a0):	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	lea	16(up), up
	movd	(up), %mm0
	adc	$0, %edx
	add	%eax, 8(rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	pmuludq	%mm7, %mm0
	inc	un
	movd	4(up), %mm1
	jnz	L(la0)

	adc	un, %edx	C un is zero here
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	adc	un, %eax
	add	%ebx, 4(rp)
	adc	un, %eax
	mov	%eax, 8(rp)

	inc	n

C ================================================================

L(ol3):	lea	12(up,n,4), up
	movd	-8(up), %mm7	C read next U invariant limb
	lea	(rp,n,4), rp	C put rp back
	mov	n, un

	movd	-4(up), %mm1
	pmuludq	%mm7, %mm1
	sar	$2, un
	movd	%mm1, %ebx
	movd	(up), %mm0
	xor	%edx, %edx	C zero edx and CF
	jmp	L(a3)

L(la3):	adc	$0, %edx
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	adc	$0, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	movd	%mm0, %eax
	movd	12(up), %mm1
	pmuludq	%mm7, %mm1
	adc	$0, %edx
	add	%ebx, 4(rp)
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	lea	16(up), up
	movd	(up), %mm0
	adc	$0, %edx
	add	%eax, 8(rp)
L(a3):	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	pmuludq	%mm7, %mm0
	inc	un
	movd	4(up), %mm1
	jnz	L(la3)

	adc	un, %edx	C un is zero here
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	adc	un, %eax
	add	%ebx, 4(rp)
	adc	un, %eax
	mov	%eax, 8(rp)

	inc	n

C ================================================================

L(ol2):	lea	8(up,n,4), up
	movd	-4(up), %mm7	C read next U invariant limb
	lea	12(rp,n,4), rp
	mov	n, un

	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	xor	%edx, %edx
	sar	$2, un
	movd	4(up), %mm1
	test	un, un		C clear carry
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	inc	un
	jnz	L(a2)
	jmp	L(re2)

L(la2):	adc	$0, %edx
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
L(a2):	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	adc	$0, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	movd	%mm0, %eax
	movd	12(up), %mm1
	pmuludq	%mm7, %mm1
	adc	$0, %edx
	add	%ebx, 4(rp)
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	lea	16(up), up
	movd	(up), %mm0
	adc	$0, %edx
	add	%eax, 8(rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	pmuludq	%mm7, %mm0
	inc	un
	movd	4(up), %mm1
	jnz	L(la2)

	adc	un, %edx	C un is zero here
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	adc	un, %eax
	add	%ebx, 4(rp)
	adc	un, %eax
	mov	%eax, 8(rp)

	inc	n
	jmp	L(ol1)

C ================================================================
L(re2):	psrlq	$32, %mm0
	movd	(up), %mm7	C read next U invariant limb
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	lea	4(rp), rp
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	movd	4(up), %mm1
	adc	un, %eax
	add	%ebx, (rp)
	pmuludq	%mm7, %mm1
	adc	un, %eax
	mov	%eax, 4(rp)
	movd	%mm1, %ebx

L(re1):	psrlq	$32, %mm1
	add	%ebx, 4(rp)
	movd	%mm1, %eax
	adc	un, %eax
	xor	n, n		C make n zeroness assumption below true
	mov	%eax, 8(rp)

L(done):			C n is zero here
	mov	24(%esp), up
	mov	28(%esp), %eax

	movd	(up), %mm0
	inc	%eax
	pmuludq	%mm0, %mm0
	lea	4(up), up
	mov	20(%esp), rp
	shr	%eax
	movd	%mm0, (rp)
	psrlq	$32, %mm0
	lea	-12(rp), rp
	mov	%eax, 28(%esp)
	jnc	L(odd)

	movd	%mm0, %ebp
	movd	(up), %mm0
	lea	8(rp), rp
	pmuludq	%mm0, %mm0
	lea	-4(up), up
	add	8(rp), %ebp
	movd	%mm0, %edx
	adc	12(rp), %edx
	rcr	n
	jmp	L(ent)

C	ALIGN(16)		C alignment seems irrelevant
L(top):	movd	(up), %mm1
	adc	n, n
	movd	%mm0, %eax
	pmuludq	%mm1, %mm1
	movd	4(up), %mm0
	adc	(rp), %eax
	movd	%mm1, %ebx
	pmuludq	%mm0, %mm0
	psrlq	$32, %mm1
	adc	4(rp), %ebx
	movd	%mm1, %ebp
	movd	%mm0, %edx
	adc	8(rp), %ebp
	adc	12(rp), %edx
	rcr	n		C FIXME: isn't this awfully slow on atom???
	adc	%eax, (rp)
	adc	%ebx, 4(rp)
L(ent):	lea	8(up), up
	adc	%ebp, 8(rp)
	psrlq	$32, %mm0
	adc	%edx, 12(rp)
L(odd):	decl	28(%esp)
	lea	16(rp), rp
	jnz	L(top)

L(end):	adc	n, n
	movd	%mm0, %eax
	adc	n, %eax
	mov	%eax, (rp)

L(rtn):	emms
	pop	%ebp
	pop	%ebx
	pop	%esi
	pop	%edi
	ret

L(one):	pmuludq	%mm7, %mm7
	movq	%mm7, -4(rp)
	emms
	pop	%esi
	pop	%edi
	ret
EPILOGUE()
@


1.1.1.1
log
@initial import GMP 5.1.3 sources.  changes include:

fixes for:
- mpn_sbpi1_div_qr_sec and mpn_sbpi1_div_r_sec
- mpz_powm_ui
- AMD family 11h
- mpz_powm_sec and mpn_powm_sec
- ASSERT() fixes
- gcd, gcdext, and invert function fixes
- some PPC division operations
@
text
@@


1.1.1.2
log
@initial import of GMP 6.1.2.  main changes from 5.1.3 below.

notes:
 - support for thumb-less ARM chips was in our port of 5.1.3, but a
   similar method has been provided upstream now
 - someone should look at the AVX failure reports, and fix them

Changes between GMP version 6.1.0 and 6.1.1

  FEATURES
  * Work around faulty cpuid on some recent Intel chips (this allows GMP to run
    on Skylake Pentiums).
  * Support thumb-less ARM chips.

Changes between GMP version 6.0.* and 6.1.0

  BUGS FIXED
  * The public function mpn_com is now correctly declared in gmp.h.
  * Healed possible failures of mpn_sec_sqr for non-cryptographic sizes for
    some obsolete CPUs.
  * Various problems related to precision for mpf have been fixed.
  * Fixed ABI incompatible stack alignment in calls from assembly code.
  * Fixed PIC bug in popcount affecting Intel processors using the 32-bit ABI.
  SPEEDUPS
  * Speedup for Intel Broadwell and Skylake through assembly code making use of
    new ADX instructions.
  * Square root is now faster when the remainder is not needed. Also the speed
    to compute the k-th root improved, for small sizes.
  FEATURES
  * New C++ functions gcd and lcm for mpz_class.
  * New public mpn functions mpn_divexact_1, mpn_zero_p, and mpn_cnd_swap.
  * New public mpq_cmp_z function, to efficiently compare rationals with
    integers.
  * Support for more 32-bit arm processors.
  * Support for AVX-less modern x86 CPUs. (Such support might be missing either
    because the CPU vendor chose to disable AVX, or because the running kernel
    lacks AVX context switch support.)
  * Support for NetBSD under Xen; we switch off AVX unconditionally under
    NetBSD since a bug in NetBSD makes AVX fail under Xen.
  MISC
  * Tuned values for FFT multiplications are provided for larger number on
    many platforms.

Changes between GMP version 5.1.* and 6.0.0
  BUGS FIXED
  * The function mpz_invert now considers any number invertible in Z/1Z.
  * The mpn multiply code now handles operands of more than 2^31 limbs
    correctly.  (Note however that the mpz code is limited to 2^32 bits on
    32-bit hosts and 2^37 bits on 64-bit hosts.)
  SPEEDUPS
  * Plain division of large operands is faster and more monotonous in operand
    size.
  * Major speedup for ARM, in particular ARM Cortex-A15, thanks to improved
    assembly.
  * Speedup for Intel Sandy Bridge, Ivy Bridge, Haswell, thanks to rewritten
    and vastly expanded assembly support.  Speedup also for the older Core 2
    and Nehalem.
  * Faster mixed arithmetic between mpq_class and double.
  FEATURES
  * Support for new Intel and AMD CPUs.
  * New public functions mpn_sec_mul and mpn_sec_sqr, implementing side-channel
    silent multiplication and squaring.
  * New public functions mpn_sec_div_qr and mpn_sec_div_r, implementing
    side-channel silent division.
  * New public functions mpn_cnd_add_n and mpn_cnd_sub_n.  Side-channel silent
    conditional addition and subtraction.
  * New public function mpn_sec_powm, implementing side-channel silent modexp.
  * New public function mpn_sec_invert, implementing side-channel silent
    modular inversion.
  * Better support for applications which use the mpz_t type, but nevertheless
    need to call some of the lower-level mpn functions.  See the documentation
    for mpz_limbs_read and related functions.
@
text
@d4 1
a4 1

d6 1
a6 1

d10 3
a12 13
dnl  it under the terms of either:
dnl
dnl    * the GNU Lesser General Public License as published by the Free
dnl      Software Foundation; either version 3 of the License, or (at your
dnl      option) any later version.
dnl
dnl  or
dnl
dnl    * the GNU General Public License as published by the Free Software
dnl      Foundation; either version 2 of the License, or (at your option) any
dnl      later version.
dnl
dnl  or both in parallel, as here.
d16 2
a17 2
dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
dnl  for more details.
d19 2
a20 3
dnl  You should have received copies of the GNU General Public License and the
dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
dnl  see https://www.gnu.org/licenses/.
@


1.1.1.1.8.1
log
@file sqr_basecase.asm was added on branch tls-maxphys on 2014-08-19 23:59:54 +0000
@
text
@d1 623
@


1.1.1.1.8.2
log
@Rebase to HEAD as of a few days ago.
@
text
@a0 623
dnl  x86 mpn_sqr_basecase -- square an mpn number, optimised for atom.

dnl  Contributed to the GNU project by Torbjorn Granlund and Marco Bodrato.
dnl
dnl  Copyright 2011 Free Software Foundation, Inc.
dnl
dnl  This file is part of the GNU MP Library.
dnl
dnl  The GNU MP Library is free software; you can redistribute it and/or modify
dnl  it under the terms of the GNU Lesser General Public License as published
dnl  by the Free Software Foundation; either version 3 of the License, or (at
dnl  your option) any later version.
dnl
dnl  The GNU MP Library is distributed in the hope that it will be useful, but
dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
dnl  License for more details.
dnl
dnl  You should have received a copy of the GNU Lesser General Public License
dnl  along with the GNU MP Library.  If not, see http://www.gnu.org/licenses/.

include(`../config.m4')

C TODO
C  * Check if 'jmp N(%esp)' is well-predicted enough to allow us to combine the
C    4 large loops into one; we could use it for the outer loop branch.
C  * Optimise code outside of inner loops.
C  * Write combined addmul_1 feed-in a wind-down code, and use when iterating
C    outer each loop.  ("Overlapping software pipelining")
C  * Perhaps use caller-saves regs for inlined mul_1, allowing us to postpone
C    all pushes.
C  * Perhaps write special code for n < M, for some small M.
C  * Replace inlined addmul_1 with smaller code from aorsmul_1.asm, or perhaps
C    with even less pipelined code.
C  * We run the outer loop until we have a 2-limb by 1-limb addmul_1 left.
C    Consider breaking out earlier, saving high the cost of short loops.

C void mpn_sqr_basecase (mp_ptr wp,
C                        mp_srcptr xp, mp_size_t xn);

define(`rp',  `%edi')
define(`up',  `%esi')
define(`n',   `%ecx')

define(`un',  `%ebp')

	TEXT
	ALIGN(16)
PROLOGUE(mpn_sqr_basecase)
	push	%edi
	push	%esi
	mov	12(%esp), rp
	mov	16(%esp), up
	mov	20(%esp), n

	lea	4(rp), rp	C write triangular product starting at rp[1]
	dec	n
	movd	(up), %mm7

	jz	L(one)
	lea	4(up), up
	push	%ebx
	push	%ebp
	mov	n, %eax

	movd	(up), %mm0
	neg	n
	pmuludq	%mm7, %mm0
	pxor	%mm6, %mm6
	mov	n, un

	and	$3, %eax
	jz	L(of0)
	cmp	$2, %eax
	jc	L(of1)
	jz	L(of2)

C ================================================================
	jmp	L(m3)
	ALIGN(16)
L(lm3):	movd	-4(up), %mm0
	pmuludq	%mm7, %mm0
	psrlq	$32, %mm6
	lea	16(rp), rp
	paddq	%mm0, %mm6
	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -4(rp)
	psrlq	$32, %mm6
L(m3):	paddq	%mm0, %mm6
	movd	4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, (rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, 4(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	add	$4, un
	movd	%mm6, 8(rp)
	lea	16(up), up
	js	L(lm3)

	psrlq	$32, %mm6
	movd	%mm6, 12(rp)

	inc	n
C	jz	L(done)
  lea	-12(up), up
  lea	4(rp), rp
	jmp	L(ol2)

C ================================================================
	ALIGN(16)
L(lm0):	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	psrlq	$32, %mm6
	lea	16(rp), rp
L(of0):	paddq	%mm0, %mm6
	movd	4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, (rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, 4(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	12(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, 8(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	add	$4, un
	movd	%mm6, 12(rp)
	lea	16(up), up
	js	L(lm0)

	psrlq	$32, %mm6
	movd	%mm6, 16(rp)

	inc	n
C	jz	L(done)
  lea	-8(up), up
  lea	8(rp), rp
	jmp	L(ol3)

C ================================================================
	ALIGN(16)
L(lm1):	movd	-12(up), %mm0
	pmuludq	%mm7, %mm0
	psrlq	$32, %mm6
	lea	16(rp), rp
	paddq	%mm0, %mm6
	movd	-8(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -12(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	-4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -8(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -4(rp)
	psrlq	$32, %mm6
L(of1):	paddq	%mm0, %mm6
	add	$4, un
	movd	%mm6, (rp)
	lea	16(up), up
	js	L(lm1)

	psrlq	$32, %mm6
	movd	%mm6, 4(rp)

	inc	n
	jz	L(done)		C goes away when we add special n=2 code
  lea	-20(up), up
  lea	-4(rp), rp
	jmp	L(ol0)

C ================================================================
	ALIGN(16)
L(lm2):	movd	-8(up), %mm0
	pmuludq	%mm7, %mm0
	psrlq	$32, %mm6
	lea	16(rp), rp
	paddq	%mm0, %mm6
	movd	-4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -8(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -4(rp)
	psrlq	$32, %mm6
L(of2):	paddq	%mm0, %mm6
	movd	4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, (rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	add	$4, un
	movd	%mm6, 4(rp)
	lea	16(up), up
	js	L(lm2)

	psrlq	$32, %mm6
	movd	%mm6, 8(rp)

	inc	n
C	jz	L(done)
  lea	-16(up), up
C  lea	(rp), rp
C	jmp	L(ol1)

C ================================================================

L(ol1):	lea	4(up,n,4), up
	movd	(up), %mm7	C read next U invariant limb
	lea	8(rp,n,4), rp
	mov	n, un

	movd	4(up), %mm1
	pmuludq	%mm7, %mm1
	sar	$2, un
	movd	%mm1, %ebx
	inc	un
	jz	L(re1)

	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	xor	%edx, %edx	C zero edx and CF
	jmp	L(a1)

L(la1):	adc	$0, %edx
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	adc	$0, %edx
	add	%eax, (rp)
L(a1):	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	movd	%mm0, %eax
	movd	12(up), %mm1
	pmuludq	%mm7, %mm1
	adc	$0, %edx
	add	%ebx, 4(rp)
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	lea	16(up), up
	movd	(up), %mm0
	adc	$0, %edx
	add	%eax, 8(rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	pmuludq	%mm7, %mm0
	inc	un
	movd	4(up), %mm1
	jnz	L(la1)

	adc	un, %edx	C un is zero here
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	adc	un, %eax
	add	%ebx, 4(rp)
	adc	un, %eax
	mov	%eax, 8(rp)

	inc	n

C ================================================================

L(ol0):	lea	(up,n,4), up
	movd	4(up), %mm7	C read next U invariant limb
	lea	4(rp,n,4), rp
	mov	n, un

	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	sar	$2, un
	movd	12(up), %mm1
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	xor	%edx, %edx	C zero edx and CF
	jmp	L(a0)

L(la0):	adc	$0, %edx
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	adc	$0, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	movd	%mm0, %eax
	movd	12(up), %mm1
	pmuludq	%mm7, %mm1
	adc	$0, %edx
	add	%ebx, 4(rp)
L(a0):	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	lea	16(up), up
	movd	(up), %mm0
	adc	$0, %edx
	add	%eax, 8(rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	pmuludq	%mm7, %mm0
	inc	un
	movd	4(up), %mm1
	jnz	L(la0)

	adc	un, %edx	C un is zero here
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	adc	un, %eax
	add	%ebx, 4(rp)
	adc	un, %eax
	mov	%eax, 8(rp)

	inc	n

C ================================================================

L(ol3):	lea	12(up,n,4), up
	movd	-8(up), %mm7	C read next U invariant limb
	lea	(rp,n,4), rp	C put rp back
	mov	n, un

	movd	-4(up), %mm1
	pmuludq	%mm7, %mm1
	sar	$2, un
	movd	%mm1, %ebx
	movd	(up), %mm0
	xor	%edx, %edx	C zero edx and CF
	jmp	L(a3)

L(la3):	adc	$0, %edx
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	adc	$0, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	movd	%mm0, %eax
	movd	12(up), %mm1
	pmuludq	%mm7, %mm1
	adc	$0, %edx
	add	%ebx, 4(rp)
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	lea	16(up), up
	movd	(up), %mm0
	adc	$0, %edx
	add	%eax, 8(rp)
L(a3):	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	pmuludq	%mm7, %mm0
	inc	un
	movd	4(up), %mm1
	jnz	L(la3)

	adc	un, %edx	C un is zero here
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	adc	un, %eax
	add	%ebx, 4(rp)
	adc	un, %eax
	mov	%eax, 8(rp)

	inc	n

C ================================================================

L(ol2):	lea	8(up,n,4), up
	movd	-4(up), %mm7	C read next U invariant limb
	lea	12(rp,n,4), rp
	mov	n, un

	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	xor	%edx, %edx
	sar	$2, un
	movd	4(up), %mm1
	test	un, un		C clear carry
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	inc	un
	jnz	L(a2)
	jmp	L(re2)

L(la2):	adc	$0, %edx
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
L(a2):	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	adc	$0, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	movd	%mm0, %eax
	movd	12(up), %mm1
	pmuludq	%mm7, %mm1
	adc	$0, %edx
	add	%ebx, 4(rp)
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	lea	16(up), up
	movd	(up), %mm0
	adc	$0, %edx
	add	%eax, 8(rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	pmuludq	%mm7, %mm0
	inc	un
	movd	4(up), %mm1
	jnz	L(la2)

	adc	un, %edx	C un is zero here
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	adc	un, %eax
	add	%ebx, 4(rp)
	adc	un, %eax
	mov	%eax, 8(rp)

	inc	n
	jmp	L(ol1)

C ================================================================
L(re2):	psrlq	$32, %mm0
	movd	(up), %mm7	C read next U invariant limb
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	lea	4(rp), rp
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	movd	4(up), %mm1
	adc	un, %eax
	add	%ebx, (rp)
	pmuludq	%mm7, %mm1
	adc	un, %eax
	mov	%eax, 4(rp)
	movd	%mm1, %ebx

L(re1):	psrlq	$32, %mm1
	add	%ebx, 4(rp)
	movd	%mm1, %eax
	adc	un, %eax
	xor	n, n		C make n zeroness assumption below true
	mov	%eax, 8(rp)

L(done):			C n is zero here
	mov	24(%esp), up
	mov	28(%esp), %eax

	movd	(up), %mm0
	inc	%eax
	pmuludq	%mm0, %mm0
	lea	4(up), up
	mov	20(%esp), rp
	shr	%eax
	movd	%mm0, (rp)
	psrlq	$32, %mm0
	lea	-12(rp), rp
	mov	%eax, 28(%esp)
	jnc	L(odd)

	movd	%mm0, %ebp
	movd	(up), %mm0
	lea	8(rp), rp
	pmuludq	%mm0, %mm0
	lea	-4(up), up
	add	8(rp), %ebp
	movd	%mm0, %edx
	adc	12(rp), %edx
	rcr	n
	jmp	L(ent)

C	ALIGN(16)		C alignment seems irrelevant
L(top):	movd	(up), %mm1
	adc	n, n
	movd	%mm0, %eax
	pmuludq	%mm1, %mm1
	movd	4(up), %mm0
	adc	(rp), %eax
	movd	%mm1, %ebx
	pmuludq	%mm0, %mm0
	psrlq	$32, %mm1
	adc	4(rp), %ebx
	movd	%mm1, %ebp
	movd	%mm0, %edx
	adc	8(rp), %ebp
	adc	12(rp), %edx
	rcr	n		C FIXME: isn't this awfully slow on atom???
	adc	%eax, (rp)
	adc	%ebx, 4(rp)
L(ent):	lea	8(up), up
	adc	%ebp, 8(rp)
	psrlq	$32, %mm0
	adc	%edx, 12(rp)
L(odd):	decl	28(%esp)
	lea	16(rp), rp
	jnz	L(top)

L(end):	adc	n, n
	movd	%mm0, %eax
	adc	n, %eax
	mov	%eax, (rp)

L(rtn):	emms
	pop	%ebp
	pop	%ebx
	pop	%esi
	pop	%edi
	ret

L(one):	pmuludq	%mm7, %mm7
	movq	%mm7, -4(rp)
	emms
	pop	%esi
	pop	%edi
	ret
EPILOGUE()
@


1.1.1.1.4.1
log
@file sqr_basecase.asm was added on branch yamt-pagecache on 2014-05-22 14:09:05 +0000
@
text
@d1 623
@


1.1.1.1.4.2
log
@sync with head.

for a reference, the tree before this commit was tagged
as yamt-pagecache-tag8.

this commit was splitted into small chunks to avoid
a limitation of cvs.  ("Protocol error: too many arguments")
@
text
@a0 623
dnl  x86 mpn_sqr_basecase -- square an mpn number, optimised for atom.

dnl  Contributed to the GNU project by Torbjorn Granlund and Marco Bodrato.
dnl
dnl  Copyright 2011 Free Software Foundation, Inc.
dnl
dnl  This file is part of the GNU MP Library.
dnl
dnl  The GNU MP Library is free software; you can redistribute it and/or modify
dnl  it under the terms of the GNU Lesser General Public License as published
dnl  by the Free Software Foundation; either version 3 of the License, or (at
dnl  your option) any later version.
dnl
dnl  The GNU MP Library is distributed in the hope that it will be useful, but
dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
dnl  License for more details.
dnl
dnl  You should have received a copy of the GNU Lesser General Public License
dnl  along with the GNU MP Library.  If not, see http://www.gnu.org/licenses/.

include(`../config.m4')

C TODO
C  * Check if 'jmp N(%esp)' is well-predicted enough to allow us to combine the
C    4 large loops into one; we could use it for the outer loop branch.
C  * Optimise code outside of inner loops.
C  * Write combined addmul_1 feed-in a wind-down code, and use when iterating
C    outer each loop.  ("Overlapping software pipelining")
C  * Perhaps use caller-saves regs for inlined mul_1, allowing us to postpone
C    all pushes.
C  * Perhaps write special code for n < M, for some small M.
C  * Replace inlined addmul_1 with smaller code from aorsmul_1.asm, or perhaps
C    with even less pipelined code.
C  * We run the outer loop until we have a 2-limb by 1-limb addmul_1 left.
C    Consider breaking out earlier, saving high the cost of short loops.

C void mpn_sqr_basecase (mp_ptr wp,
C                        mp_srcptr xp, mp_size_t xn);

define(`rp',  `%edi')
define(`up',  `%esi')
define(`n',   `%ecx')

define(`un',  `%ebp')

	TEXT
	ALIGN(16)
PROLOGUE(mpn_sqr_basecase)
	push	%edi
	push	%esi
	mov	12(%esp), rp
	mov	16(%esp), up
	mov	20(%esp), n

	lea	4(rp), rp	C write triangular product starting at rp[1]
	dec	n
	movd	(up), %mm7

	jz	L(one)
	lea	4(up), up
	push	%ebx
	push	%ebp
	mov	n, %eax

	movd	(up), %mm0
	neg	n
	pmuludq	%mm7, %mm0
	pxor	%mm6, %mm6
	mov	n, un

	and	$3, %eax
	jz	L(of0)
	cmp	$2, %eax
	jc	L(of1)
	jz	L(of2)

C ================================================================
	jmp	L(m3)
	ALIGN(16)
L(lm3):	movd	-4(up), %mm0
	pmuludq	%mm7, %mm0
	psrlq	$32, %mm6
	lea	16(rp), rp
	paddq	%mm0, %mm6
	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -4(rp)
	psrlq	$32, %mm6
L(m3):	paddq	%mm0, %mm6
	movd	4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, (rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, 4(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	add	$4, un
	movd	%mm6, 8(rp)
	lea	16(up), up
	js	L(lm3)

	psrlq	$32, %mm6
	movd	%mm6, 12(rp)

	inc	n
C	jz	L(done)
  lea	-12(up), up
  lea	4(rp), rp
	jmp	L(ol2)

C ================================================================
	ALIGN(16)
L(lm0):	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	psrlq	$32, %mm6
	lea	16(rp), rp
L(of0):	paddq	%mm0, %mm6
	movd	4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, (rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, 4(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	12(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, 8(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	add	$4, un
	movd	%mm6, 12(rp)
	lea	16(up), up
	js	L(lm0)

	psrlq	$32, %mm6
	movd	%mm6, 16(rp)

	inc	n
C	jz	L(done)
  lea	-8(up), up
  lea	8(rp), rp
	jmp	L(ol3)

C ================================================================
	ALIGN(16)
L(lm1):	movd	-12(up), %mm0
	pmuludq	%mm7, %mm0
	psrlq	$32, %mm6
	lea	16(rp), rp
	paddq	%mm0, %mm6
	movd	-8(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -12(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	-4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -8(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -4(rp)
	psrlq	$32, %mm6
L(of1):	paddq	%mm0, %mm6
	add	$4, un
	movd	%mm6, (rp)
	lea	16(up), up
	js	L(lm1)

	psrlq	$32, %mm6
	movd	%mm6, 4(rp)

	inc	n
	jz	L(done)		C goes away when we add special n=2 code
  lea	-20(up), up
  lea	-4(rp), rp
	jmp	L(ol0)

C ================================================================
	ALIGN(16)
L(lm2):	movd	-8(up), %mm0
	pmuludq	%mm7, %mm0
	psrlq	$32, %mm6
	lea	16(rp), rp
	paddq	%mm0, %mm6
	movd	-4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -8(rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, -4(rp)
	psrlq	$32, %mm6
L(of2):	paddq	%mm0, %mm6
	movd	4(up), %mm0
	pmuludq	%mm7, %mm0
	movd	%mm6, (rp)
	psrlq	$32, %mm6
	paddq	%mm0, %mm6
	add	$4, un
	movd	%mm6, 4(rp)
	lea	16(up), up
	js	L(lm2)

	psrlq	$32, %mm6
	movd	%mm6, 8(rp)

	inc	n
C	jz	L(done)
  lea	-16(up), up
C  lea	(rp), rp
C	jmp	L(ol1)

C ================================================================

L(ol1):	lea	4(up,n,4), up
	movd	(up), %mm7	C read next U invariant limb
	lea	8(rp,n,4), rp
	mov	n, un

	movd	4(up), %mm1
	pmuludq	%mm7, %mm1
	sar	$2, un
	movd	%mm1, %ebx
	inc	un
	jz	L(re1)

	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	xor	%edx, %edx	C zero edx and CF
	jmp	L(a1)

L(la1):	adc	$0, %edx
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	adc	$0, %edx
	add	%eax, (rp)
L(a1):	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	movd	%mm0, %eax
	movd	12(up), %mm1
	pmuludq	%mm7, %mm1
	adc	$0, %edx
	add	%ebx, 4(rp)
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	lea	16(up), up
	movd	(up), %mm0
	adc	$0, %edx
	add	%eax, 8(rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	pmuludq	%mm7, %mm0
	inc	un
	movd	4(up), %mm1
	jnz	L(la1)

	adc	un, %edx	C un is zero here
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	adc	un, %eax
	add	%ebx, 4(rp)
	adc	un, %eax
	mov	%eax, 8(rp)

	inc	n

C ================================================================

L(ol0):	lea	(up,n,4), up
	movd	4(up), %mm7	C read next U invariant limb
	lea	4(rp,n,4), rp
	mov	n, un

	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	sar	$2, un
	movd	12(up), %mm1
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	xor	%edx, %edx	C zero edx and CF
	jmp	L(a0)

L(la0):	adc	$0, %edx
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	adc	$0, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	movd	%mm0, %eax
	movd	12(up), %mm1
	pmuludq	%mm7, %mm1
	adc	$0, %edx
	add	%ebx, 4(rp)
L(a0):	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	lea	16(up), up
	movd	(up), %mm0
	adc	$0, %edx
	add	%eax, 8(rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	pmuludq	%mm7, %mm0
	inc	un
	movd	4(up), %mm1
	jnz	L(la0)

	adc	un, %edx	C un is zero here
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	adc	un, %eax
	add	%ebx, 4(rp)
	adc	un, %eax
	mov	%eax, 8(rp)

	inc	n

C ================================================================

L(ol3):	lea	12(up,n,4), up
	movd	-8(up), %mm7	C read next U invariant limb
	lea	(rp,n,4), rp	C put rp back
	mov	n, un

	movd	-4(up), %mm1
	pmuludq	%mm7, %mm1
	sar	$2, un
	movd	%mm1, %ebx
	movd	(up), %mm0
	xor	%edx, %edx	C zero edx and CF
	jmp	L(a3)

L(la3):	adc	$0, %edx
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	adc	$0, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	movd	%mm0, %eax
	movd	12(up), %mm1
	pmuludq	%mm7, %mm1
	adc	$0, %edx
	add	%ebx, 4(rp)
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	lea	16(up), up
	movd	(up), %mm0
	adc	$0, %edx
	add	%eax, 8(rp)
L(a3):	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	pmuludq	%mm7, %mm0
	inc	un
	movd	4(up), %mm1
	jnz	L(la3)

	adc	un, %edx	C un is zero here
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	adc	un, %eax
	add	%ebx, 4(rp)
	adc	un, %eax
	mov	%eax, 8(rp)

	inc	n

C ================================================================

L(ol2):	lea	8(up,n,4), up
	movd	-4(up), %mm7	C read next U invariant limb
	lea	12(rp,n,4), rp
	mov	n, un

	movd	(up), %mm0
	pmuludq	%mm7, %mm0
	xor	%edx, %edx
	sar	$2, un
	movd	4(up), %mm1
	test	un, un		C clear carry
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	inc	un
	jnz	L(a2)
	jmp	L(re2)

L(la2):	adc	$0, %edx
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
L(a2):	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	movd	8(up), %mm0
	pmuludq	%mm7, %mm0
	adc	$0, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	movd	%mm0, %eax
	movd	12(up), %mm1
	pmuludq	%mm7, %mm1
	adc	$0, %edx
	add	%ebx, 4(rp)
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	lea	16(up), up
	movd	(up), %mm0
	adc	$0, %edx
	add	%eax, 8(rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %edx
	pmuludq	%mm7, %mm0
	inc	un
	movd	4(up), %mm1
	jnz	L(la2)

	adc	un, %edx	C un is zero here
	add	%ebx, 12(rp)
	movd	%mm0, %eax
	pmuludq	%mm7, %mm1
	lea	16(rp), rp
	psrlq	$32, %mm0
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	adc	un, %eax
	add	%ebx, 4(rp)
	adc	un, %eax
	mov	%eax, 8(rp)

	inc	n
	jmp	L(ol1)

C ================================================================
L(re2):	psrlq	$32, %mm0
	movd	(up), %mm7	C read next U invariant limb
	adc	%edx, %eax
	movd	%mm0, %edx
	movd	%mm1, %ebx
	adc	un, %edx
	add	%eax, (rp)
	lea	4(rp), rp
	psrlq	$32, %mm1
	adc	%edx, %ebx
	movd	%mm1, %eax
	movd	4(up), %mm1
	adc	un, %eax
	add	%ebx, (rp)
	pmuludq	%mm7, %mm1
	adc	un, %eax
	mov	%eax, 4(rp)
	movd	%mm1, %ebx

L(re1):	psrlq	$32, %mm1
	add	%ebx, 4(rp)
	movd	%mm1, %eax
	adc	un, %eax
	xor	n, n		C make n zeroness assumption below true
	mov	%eax, 8(rp)

L(done):			C n is zero here
	mov	24(%esp), up
	mov	28(%esp), %eax

	movd	(up), %mm0
	inc	%eax
	pmuludq	%mm0, %mm0
	lea	4(up), up
	mov	20(%esp), rp
	shr	%eax
	movd	%mm0, (rp)
	psrlq	$32, %mm0
	lea	-12(rp), rp
	mov	%eax, 28(%esp)
	jnc	L(odd)

	movd	%mm0, %ebp
	movd	(up), %mm0
	lea	8(rp), rp
	pmuludq	%mm0, %mm0
	lea	-4(up), up
	add	8(rp), %ebp
	movd	%mm0, %edx
	adc	12(rp), %edx
	rcr	n
	jmp	L(ent)

C	ALIGN(16)		C alignment seems irrelevant
L(top):	movd	(up), %mm1
	adc	n, n
	movd	%mm0, %eax
	pmuludq	%mm1, %mm1
	movd	4(up), %mm0
	adc	(rp), %eax
	movd	%mm1, %ebx
	pmuludq	%mm0, %mm0
	psrlq	$32, %mm1
	adc	4(rp), %ebx
	movd	%mm1, %ebp
	movd	%mm0, %edx
	adc	8(rp), %ebp
	adc	12(rp), %edx
	rcr	n		C FIXME: isn't this awfully slow on atom???
	adc	%eax, (rp)
	adc	%ebx, 4(rp)
L(ent):	lea	8(up), up
	adc	%ebp, 8(rp)
	psrlq	$32, %mm0
	adc	%edx, 12(rp)
L(odd):	decl	28(%esp)
	lea	16(rp), rp
	jnz	L(top)

L(end):	adc	n, n
	movd	%mm0, %eax
	adc	n, %eax
	mov	%eax, (rp)

L(rtn):	emms
	pop	%ebp
	pop	%ebx
	pop	%esi
	pop	%edi
	ret

L(one):	pmuludq	%mm7, %mm7
	movq	%mm7, -4(rp)
	emms
	pop	%esi
	pop	%edi
	ret
EPILOGUE()
@